English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present a novel feature attribution method for explaining textclassifiers, and analyze it in the context of hate speech detection. Althoughfeature attribution models usually provide a single importance score for eachtoken, we instead provide two complementary and theoretically-grounded scores-- necessity and sufficiency -- resulting in more informative explanations. Wepropose a transparent method that calculates these values by generatingexplicit perturbations of the input text, allowing the importance scoresthemselves to be explainable. We employ our method to explain the predictionsof different hate speech detection models on the same set of curated examplesfrom a test suite, and show that different values of necessity and sufficiencyfor identity terms correspond to different kinds of false positive errors,exposing sources of classifier bias against marginalized groups.

Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection